Audit commercial resilience claim integrity

What it's for

Stops architecture and reliability business cases from adding the same contract or revenue exposure once per component, while showing exactly which claims need finance or evidence repair.

What you give it

Inputs split into evidence read from your connected systems, calibration your team owns, and numerical controls that affect precision but never the result's meaning.

{
  "action_effects": [
    {
      "action_id": "harden-api",
      "component_id": "api",
      "evidence_verified": true,
      "id": "harden-api-effect",
      "residual_loss_multipliers": [
        0.2,
        0.2,
        0.2,
        0.2
      ]
    },
    {
      "action_id": "harden-database",
      "component_id": "database",
      "evidence_verified": true,
      "id": "harden-database-effect",
      "residual_loss_multipliers": [
        0.5,
        0.5,
        0.5,
        0.5
      ]
    }
  ],
  "commercial_sources": [
    {
      "evidence_verified": true,
      "id": "enterprise-contract",
      "value_at_risk": 100
    },
    {
      "evidence_verified": true,
      "id": "usage-margin",
      "value_at_risk": 200
    }
  ],
  "components": [
    {
      "evidence_verified": true,
      "id": "api"
    },

What you get back

This is the actual output of running the example above — computed by the same function the platform calls, not an illustration.

{
  "action_diagnostics": [
    {
      "action_id": "harden-api",
      "claim_overstatement_fraction": 0,
      "effect_count": 1,
      "evidence_verified": true,
      "expected_claim_overstatement": 0,
      "expected_claimed_avoided_loss": 20,
      "expected_graph_modeled_avoided_loss": 20,
      "expected_supported_claim": 20,
      "failed_gates": []
    },
    {
      "action_id": "harden-database",
      "claim_overstatement_fraction": 0,
      "effect_count": 1,
      "evidence_verified": true,
      "expected_claim_overstatement": 0,
      "expected_claimed_avoided_loss": 35,
      "expected_graph_modeled_avoided_loss": 35,
      "expected_supported_claim": 35,
      "failed_gates": []
    }
  ],
  "assumptions": [
    "Every commercial source is a unique finance-governed contribution, penalty, relationship or cash exposure on one horizon; source-component fractions represent incremental loss conditional on component failure and combine as retained-value survival rather than additive credits.",
    "Action effects are prospective residual-loss multipliers with point-in-time evidence. The audit recomputes each action alone and caps supported claims at graph-modeled avoided loss; it does not establish causal effectiveness or add standalone claims into a portfolio benefit.",
    "A failed audit requires source, architecture, scenario or effect reconciliation. It is not evidence of fraud, customer quality, engineering blame, vendor misconduct or individual performance and does not authorize investment or personnel action."
  ],
  "configuration": {
    "maximum_claim_overstatement_fraction": 0.05,
    "maximum_probability_sum_error": 0,
    "minimum_evidence_coverage": 0.95,
    "multi_action_effect_rule": "multiplicative_residual_loss",
    "multi_component_loss_rule": "multiplicative_survival_union",
    "scenario_probability_sum": 1
  },
  "decision": "commercial_resilience_claims_supported",
  "duplicate_action_component_pairs": [],
  "method": "unique_source_graph_resilience_claim_integrity_audit_v1",
  "summary": {
    "action_count": 2,
    "commercial_source_count": 2,

How it works

Network & dependency analysis — Trace how load, failure and knowledge propagate through a graph of teams, services or components.

1. 1 Freeze unique finance-owned commercial sources, technical components, conditional-loss exposure edges and coherent joint failure scenarios on one point-in-time decision horizon.
2. 2 Apply every proposed action alone through its scenario-aligned residual-loss multipliers, combine simultaneous component failures as a multiplicative retained-value union, and compare the resulting avoided loss with the submitted claim.
3. 3 Cap supported value at graph-modeled avoided loss, retain overstatement, duplicate action-component effects, probability error and evidence gaps, and abstain unless every governed gate clears.

Before you trust it

Every tool in the catalog ships with the conditions under which its answer is meaningful — and the conditions under which it should abstain instead of guessing.

Calibrating it to your org

Calibration workflow

1. 1 Define the management decision, target outcome, aggregate unit, privacy boundary, cadence, and prediction/intervention horizon for this organization.
2. 2 Build a tenant-scoped historical cohort using only information available before each prediction or decision; preserve zero periods, censoring, assignment probabilities, and unresolved outcomes when the method requires them.
3. 3 Estimate statistical parameters on training history, but obtain costs, utilities, risk tolerance, practical-effect thresholds, capacity, and policy constraints from accountable decision owners.
4. 4 Validate on later time windows or held-out aggregate units at the deployment grain, against a simple baseline and the function-specific validation strategy.
5. 5 Deploy only if the returned decision clears evidence, overlap, calibration, robustness, and guardrail checks; warning, unsupported, schema-gap, and fallback decisions are abstentions.
6. 6 Monitor realized outcomes, data drift, coverage, and decision regret; recalibrate at a governed cadence or after a detected regime/definition change, never merely because a stakeholder dislikes the result.

Call it from your AI

You don't wire up 388 tools in your MCP client. The GitRevio MCP server exposes 18 tools, three of which let an agent search the catalog, read a tool's schema, and run it — so the assistant finds this one on its own.

gitrevio_capabilities_search
  { "q": "audit resilience roi claims against a" }
  → finds "audit_commercial_resilience_claim_integrity"

gitrevio_capability_describe
  { "capability_id": "audit_commercial_resilience_claim_integrity" }
  → returns the input schema and agent guidance shown on this page

gitrevio_capability_run
  { "capability_id": "audit_commercial_resilience_claim_integrity", "arguments": { ... } }
  → returns the result shown above

Works in Claude Desktop, Claude Code, Cursor, Cline, Continue.dev, Goose and Aider. See the MCP server.

Related tools

See every tool in Risk, tails & resilience →